BlogLLM Benchmark Scores as Published, Side by Side
CNMO: Results as Published
Every result the catalog holds for CNMO: 13 models from 6 developers, read from 3 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Science and MathMaintainer Chinese Mathematical Society (competition); evaluation sets assembled by model publishersIntroduced 2024Data version 2026103001, as of 2026-10-30
CNMO 2024 is the problem set of the 2024 Chinese National Mathematical Olympiad used as a math test: the model must produce the final answers to the competition problems. The score is the share answered correctly.
Not checked against a maintainer's page.
CNMO 2024
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-4.1OpenAI, released 2025-04-14 | 56.6% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| o1-miniOpenAI, released 2024-09-12 | 67.6% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| GPT-4oOpenAI, released 2024-05-13 | 10.8% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Claude Opus 4Anthropic, released 2025-05-22 | 57.6% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Claude Sonnet 4Anthropic, released 2025-05-22 | 60.4% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Claude 3.5 SonnetAnthropic, released 2024-10-22 | 13.1% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Gemini 2.5 FlashGoogle, released 2025-05-20 | 75% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| DeepSeek-R1-0528DeepSeek, released 2025-05-28 | 86.9% | DeepSeek, DeepSeek-R1-0528 model cardchecked 2026-10-15 | - |
| DeepSeek-V3-0324DeepSeek, released 2025-03-24 | 74.7% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| DeepSeek-R1DeepSeek, released 2025-01-20 | 78.8% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15; printed on 1 more page | - |
| DeepSeek-V3DeepSeek, released 2024-12-26 | 43.2% | DeepSeek, DeepSeek-R1 model cardchecked 2026-10-15 | - |
| Qwen3-235B-A22BAlibaba, released 2025-04-29 | 48.6% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: non-thinking |
| Kimi K2 InstructMoonshot AI, released 2025-07-11 | 74.3% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.